Précis Finance MCP
Server Details
Public read-only Précis Finance MCP demo with synthetic data; no account or credentials required.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- Repository
- precis-finance/precis-finance-mcp
- GitHub Stars
- 7
- Server Listing
- Précis-MCP
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 20 tools
Most tools have clear, distinct roles: metadata listing, ingestion inspection, metric/statement querying, charting, and export are separated cleanly. The main potential confusion is between the formatted-table and raw-data variants (run_metric vs run_metric_data, run_statement vs run_statement_data), but the descriptions explicitly explain when to use each.
The tool set is overwhelmingly snake_case and follows a predictable verb_noun pattern such as list_kpis, get_binding, run_metric, and inspect_rows. Exceptions like precis_orientation and eval_chart_transform are minor and still readable, though they keep naming from being perfectly uniform.
Twenty tools is on the heavy side for an MCP server, even one covering finance querying, charting, export, metadata, and ingestion inspection. Each tool has a defensible role, but the surface is broad enough that a borderline count verdict is fair.
The read-oriented analytics lifecycle is well covered: discovery, hierarchy search, metric and statement queries, raw data access, chart creation, export, inspection, and ingestion audit. Gaps are mostly around mutation/admin operations such as creating or updating bindings/scenarios and triggering loads, which may be intentionally out of scope.
Available Tools
20 toolseval_chart_transformARead-onlyInspect
Create a chart from data_refs (an array of snapshot IDs), a bounded JavaScript function, and chart_spec. Supports line, bar, area, waterfall, scatter, horizontal_bar, forecast_line, cohort_heatmap and sparkline_row. Query first and inspect rows; the transform takes one result per ref and returns flat rows. Cached values are already scaled: scale 3 means non-exempt metrics are in thousands; scale 0 means units. Percentages (75 means 75%), FTEs and other scale-exempt metrics retain their units. Do not scale again; y_scale is forced to 0. For multiple sources, inspect each scale and format; re-query same-unit series at a common scale, and use separately labelled axes for different units (line/bar/area) or separate charts. Conflicting nonempty caption scale labels are omitted; unlabelled sources leave other labels intact. Set axis unit labels explicitly.
Inputs: data_refs (required), chart_spec (required), transform_code (required).
export_datasetAInspect
Export a previously returned data_ref to json or xlsx without rerunning the query. Use this for standard Excel exports of reports already shown, rather than rebuilding their JSON with Python. Financial XLSX uses shared server formatting and retains source/region metadata for add-in conversion. Returns a temporary file/download link; an expired snapshot requires a fresh authorized query, whose values may change.
Inputs: format (required), data_ref (required).
get_bindingBRead-onlyInspect
Fetch one data feed's full configuration: source, target dataset, schedule, and extract parameters.
Inputs: binding_id (required).
get_file_downloadCRead-onlyInspect
Renew a download capability for an available, owned artifact.
Inputs: file_id (required).
get_inspection_schemaCRead-onlyInspect
Get the column schema for an inspection source.
Inputs: source_key (required).
get_load_statusARead-onlyInspect
Fetch one data load's full detail by load_id — timestamps, status, rows landed, and any error message.
Inputs: load_id (required).
inspect_rowsARead-onlyInspect
Inspect the row-level detail behind a figure, from an enabled inspection source. Returns a capped sample for reasoning plus a grid for the user.
Inputs: source_key (required), scenario_id (required), limit, columns, +3 more.
list_bindingsBRead-onlyInspect
List the configured data feeds (ingestion bindings) with their schedule — which datasets load, from where, how often.
Inputs: target, source_id.
list_dimensionsARead-onlyInspect
List the dimensions defined in the model — keys, labels, and kinds (leaf / derived / ragged hierarchy). Catalogue metadata only; use search_hierarchy to list a dimension's members.
Inputs: no named parameters.
list_inspection_sourcesBRead-onlyInspect
List the row-level sources available for inspection.
Inputs: no named parameters.
list_kpisARead-onlyInspect
Browse the metric catalogue — metric keys, formats, domains, and the dimensions available per metric.
Inputs: no named parameters.
list_load_historyBRead-onlyInspect
List data-load attempts from the ingestion audit trail — when each dataset landed, with what status. Answers "is April in yet?" / "when was this data last loaded?".
Inputs: limit, period, status, binding_id, +1 more.
list_scenariosBRead-onlyInspect
List the available planning scenarios and their status.
Inputs: no named parameters.
list_variantsCRead-onlyInspect
List the what-if variants of a scenario.
Inputs: scenario_id (required).
precis_orientationAInspect
Call this first. Returns how to use Précis over this connector: the data model (scenarios, metrics, statements, dimensions), the reporting-tool variants, and how to build charts. Read it before composing queries.
Inputs: no named parameters.
run_metricBRead-onlyInspect
Break one or more metrics down by a dimension — revenue by project, utilisation by employee, headcount trends, GL account drill-down. Rows are the dimension; columns are metrics × scenarios. Pass scenarios explicitly and give every scenario a concise, user-facing alias such as Actuals, Budget, Variance, or Var %. Returns a formatted table with structured data. The widget already displays this table to the user. Add useful interpretation; do not reproduce the table or restate all its rows in Markdown unless the user explicitly requests it or the widget is unavailable.
Inputs: metrics (required), scale, filters, decimals, +4 more.
run_metric_dataARead-onlyInspect
Break one or more metrics down by a dimension — revenue by project, utilisation by employee, headcount trends, GL account drill-down. Rows are the dimension; columns are metrics × scenarios. Pass scenarios explicitly and give every scenario a concise, user-facing alias such as Actuals, Budget, Variance, or Var %. Returns the raw figures (and a data_ref) for your own analysis or to build a chart — pass [data_ref] as data_refs to eval_chart_transform. Does not show the user a table.
Inputs: metrics (required), scale, filters, decimals, +4 more.
run_statementARead-onlyInspect
Run a financial statement — P&L, variance report, or executive summary. Rows are statement lines (Revenue, Direct Cost, Gross Margin, …); columns are scenarios. Supports an optional dimension breakdown (e.g. by period or cost centre). For an unspecified general P&L, prefer full_pnl when it is listed by precis_orientation. Give every scenario a concise, user-facing alias such as Actuals, Budget, Variance, or Var %. Returns a formatted table with structured data. The widget already displays this table to the user. Add useful interpretation; do not reproduce the table or restate all its rows in Markdown unless the user explicitly requests it or the widget is unavailable.
Inputs: scale, filters, decimals, scenarios, +4 more.
run_statement_dataARead-onlyInspect
Run a financial statement — P&L, variance report, or executive summary. Rows are statement lines (Revenue, Direct Cost, Gross Margin, …); columns are scenarios. Supports an optional dimension breakdown (e.g. by period or cost centre). For an unspecified general P&L, prefer full_pnl when it is listed by precis_orientation. Give every scenario a concise, user-facing alias such as Actuals, Budget, Variance, or Var %. Returns the raw figures (and a data_ref) for your own analysis or to build a chart — pass [data_ref] as data_refs to eval_chart_transform. Does not show the user a table.
Inputs: scale, filters, decimals, scenarios, +4 more.
search_hierarchyBRead-onlyInspect
Search the dimension hierarchies (cost centres, accounts, …) to find valid codes and ids before composing a query.
Inputs: limit, query, dimension.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Public MCP digital twin with synthetic systems and an agent firewall. No customer data.
Demo personal-finance MCP App: spending, subscriptions, and net worth as interactive UI.
Read-only educational MCP for CryptoDecentral Sovereign. No auth, trading, custody, or advice.
Governed company knowledge over MCP. Synthetic read-only demo; customer Atlas by contract.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceProvides read-only MCP tools for market snapshots, position risk, order reconciliation, and daily report previews with deterministic financial calculations, evidence chains, and audit trails.MIT
- AlicenseNot gradedqualityDmaintenanceHosted MCP server providing read-only access to US public company fundamentals, segment breakdowns, peer comparisons, and earnings data sourced directly from SEC filings.MIT
- FlicenseBqualityCmaintenanceEnables financial data retrieval, company context, market information, financial modelling, and valuation through MCP tools, with a deterministic sample provider for testing before connecting live data sources.15-
- AlicenseNot gradedqualityBmaintenanceEnables local, read-only exploration of synthetic personal banking data—accounts, balances, and paginated transactions—through MCP tools without requiring bank credentials or cloud services. The current version uses only invented fixtures and does not connect to any real bank.1MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.